| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 5530, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9, |
| "learning_rate": 4.547920433996384e-05, |
| "loss": 2.5146, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 4.095840867992767e-05, |
| "loss": 1.4992, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 3.6437613019891505e-05, |
| "loss": 1.0354, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 3.191681735985534e-05, |
| "loss": 0.7357, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.52, |
| "learning_rate": 2.7396021699819167e-05, |
| "loss": 0.5078, |
| "step": 2500 |
| }, |
| { |
| "epoch": 5.42, |
| "learning_rate": 2.2875226039783005e-05, |
| "loss": 0.3726, |
| "step": 3000 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 1.8354430379746836e-05, |
| "loss": 0.2824, |
| "step": 3500 |
| }, |
| { |
| "epoch": 7.23, |
| "learning_rate": 1.383363471971067e-05, |
| "loss": 0.1955, |
| "step": 4000 |
| }, |
| { |
| "epoch": 8.14, |
| "learning_rate": 9.312839059674505e-06, |
| "loss": 0.1599, |
| "step": 4500 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 4.792043399638336e-06, |
| "loss": 0.1064, |
| "step": 5000 |
| }, |
| { |
| "epoch": 9.95, |
| "learning_rate": 2.7124773960217e-07, |
| "loss": 0.088, |
| "step": 5500 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 5530, |
| "total_flos": 1766784934699008.0, |
| "train_loss": 0.6782714297499838, |
| "train_runtime": 520.4144, |
| "train_samples_per_second": 42.485, |
| "train_steps_per_second": 10.626 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5530, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1766784934699008.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
